INDEX
    Explanations

    mentions of countries and their related entities in a political context

    New Auto-Interp
    Negative Logits
    DockStyle
    -0.65
     Infórmanos
    -0.56
    -0.47
    Diweddarwch
    -0.42
    featureID
    -0.39
    __':
    
    -0.36
    ValueStyle
    -0.35
     Thrones
    -0.35
    انتهای
    -0.35
    unfinished
    -0.34
    POSITIVE LOGITS
     daily
    0.58
    InjectMocks
    0.46
     portal
    0.46
     Canal
    0.45
    ьаж
    0.43
    fillType
    0.43
     dzien
    0.43
     CANAL
    0.41
     channel
    0.41
    IBOutlet
    0.41
    Act Density 0.305%

    No Known Activations